October 17, 2019

3075 words 15 mins read

Paper Group ANR 806

Using Convolutional Neural Networks for Determining Reticulocyte Percentage in Cats. Scalable inference for crossed random effects models. Maximum Likelihood Estimation and Graph Matching in Errorfully Observed Networks. Network Features Based Co-hyponymy Detection. Kernel Conjugate Gradient Methods with Random Projections. Deep Interactive Evoluti …

Using Convolutional Neural Networks for Determining Reticulocyte Percentage in Cats


Title	Using Convolutional Neural Networks for Determining Reticulocyte Percentage in Cats
Authors	Krunoslav Vinicki, Pierluigi Ferrari, Maja Belic, Romana Turk
Abstract	Recent advances in artificial intelligence (AI), specifically in computer vision (CV) and deep learning (DL), have created opportunities for novel systems in many fields. In the last few years, deep learning applications have demonstrated impressive results not only in fields such as autonomous driving and robotics, but also in the field of medicine, where they have, in some cases, even exceeded human-level performance. However, despite the huge potential, adoption of deep learning-based methods is still slow in many areas, especially in veterinary medicine, where we haven’t been able to find any research papers using modern convolutional neural networks (CNNs) in medical image processing. We believe that using deep learning-based medical imaging can enable more accurate, faster and less expensive diagnoses in veterinary medicine. In order to do so, however, these methods have to be accessible to everyone in this field, not just to computer scientists. To show the potential of this technology, we present results on a real-world task in veterinary medicine that is usually done manually: feline reticulocyte percentage. Using an open source Keras implementation of the Single-Shot MultiBox Detector (SSD) model architecture and training it on only 800 labeled images, we achieve an accuracy of 98.7% at predicting the correct number of aggregate reticulocytes in microscope images of cat blood smears. The main motivation behind this paper is to show not only that deep learning can approach or even exceed human-level performance on a task like this, but also that anyone in the field can implement it, even without a background in computer science.
Tasks	Autonomous Driving
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04873v2
PDF	http://arxiv.org/pdf/1803.04873v2.pdf
PWC	https://paperswithcode.com/paper/using-convolutional-neural-networks-for
Repo
Framework

Scalable inference for crossed random effects models


Title	Scalable inference for crossed random effects models
Authors	Omiros Papaspiliopoulos, Gareth O. Roberts, Giacomo Zanella
Abstract	We analyze the complexity of Gibbs samplers for inference in crossed random effect models used in modern analysis of variance. We demonstrate that for certain designs the plain vanilla Gibbs sampler is not scalable, in the sense that its complexity is worse than proportional to the number of parameters and data. We thus propose a simple modification leading to a collapsed Gibbs sampler that is provably scalable. Although our theory requires some balancedness assumptions on the data designs, we demonstrate in simulated and real datasets that the rates it predicts match remarkably the correct rates in cases where the assumptions are violated. We also show that the collapsed Gibbs sampler, extended to sample further unknown hyperparameters, outperforms significantly alternative state of the art algorithms.
Tasks
Published	2018-03-26
URL	http://arxiv.org/abs/1803.09460v1
PDF	http://arxiv.org/pdf/1803.09460v1.pdf
PWC	https://paperswithcode.com/paper/scalable-inference-for-crossed-random-effects
Repo
Framework

Maximum Likelihood Estimation and Graph Matching in Errorfully Observed Networks


Title	Maximum Likelihood Estimation and Graph Matching in Errorfully Observed Networks
Authors	Jesús Arroyo, Daniel L. Sussman, Carey E. Priebe, Vince Lyzinski
Abstract	Given a pair of graphs with the same number of vertices, the inexact graph matching problem consists in finding a correspondence between the vertices of these graphs that minimizes the total number of induced edge disagreements. We study this problem from a statistical framework in which one of the graphs is an errorfully observed copy of the other. We introduce a corrupting channel model, and show that in this model framework, the solution to the graph matching problem is a maximum likelihood estimator. Necessary and sufficient conditions for consistency of this MLE are presented, as well as a relaxed notion of consistency in which a negligible fraction of the vertices need not be matched correctly. The results are used to study matchability in several families of random graphs, including edge independent models, random regular graphs and small-world networks. We also use these results to introduce measures of matching feasibility, and experimentally validate the results on simulated and real-world networks.
Tasks	Graph Matching
Published	2018-12-26
URL	https://arxiv.org/abs/1812.10519v3
PDF	https://arxiv.org/pdf/1812.10519v3.pdf
PWC	https://paperswithcode.com/paper/maximum-likelihood-estimation-and-graph
Repo
Framework

Network Features Based Co-hyponymy Detection


Title	Network Features Based Co-hyponymy Detection
Authors	Abhik Jana, Pawan Goyal
Abstract	Distinguishing lexical relations has been a long term pursuit in natural language processing (NLP) domain. Recently, in order to detect lexical relations like hypernymy, meronymy, co-hyponymy etc., distributional semantic models are being used extensively in some form or the other. Even though a lot of efforts have been made for detecting hypernymy relation, the problem of co-hyponymy detection has been rarely investigated. In this paper, we are proposing a novel supervised model where various network measures have been utilized to identify co-hyponymy relation with high accuracy performing better or at par with the state-of-the-art models.
Tasks
Published	2018-02-13
URL	http://arxiv.org/abs/1802.04609v1
PDF	http://arxiv.org/pdf/1802.04609v1.pdf
PWC	https://paperswithcode.com/paper/network-features-based-co-hyponymy-detection
Repo
Framework

Kernel Conjugate Gradient Methods with Random Projections


Title	Kernel Conjugate Gradient Methods with Random Projections
Authors	Junhong Lin, Volkan Cevher
Abstract	We propose and study kernel conjugate gradient methods (KCGM) with random projections for least-squares regression over a separable Hilbert space. Considering two types of random projections generated by randomized sketches and Nystr"{o}m subsampling, we prove optimal statistical results with respect to variants of norms for the algorithms under a suitable stopping rule. Particularly, our results show that if the projection dimension is proportional to the effective dimension of the problem, KCGM with randomized sketches can generalize optimally, while achieving a computational advantage. As a corollary, we derive optimal rates for classic KCGM in the case that the target function may not be in the hypothesis space, filling a theoretical gap.
Tasks
Published	2018-11-05
URL	http://arxiv.org/abs/1811.01760v1
PDF	http://arxiv.org/pdf/1811.01760v1.pdf
PWC	https://paperswithcode.com/paper/kernel-conjugate-gradient-methods-with-random
Repo
Framework

Deep Interactive Evolution


Title	Deep Interactive Evolution
Authors	Philip Bontrager, Wending Lin, Julian Togelius, Sebastian Risi
Abstract	This paper describes an approach that combines generative adversarial networks (GANs) with interactive evolutionary computation (IEC). While GANs can be trained to produce lifelike images, they are normally sampled randomly from the learned distribution, providing limited control over the resulting output. On the other hand, interactive evolution has shown promise in creating various artifacts such as images, music and 3D objects, but traditionally relies on a hand-designed evolvable representation of the target domain. The main insight in this paper is that a GAN trained on a specific target domain can act as a compact and robust genotype-to-phenotype mapping (i.e. most produced phenotypes do resemble valid domain artifacts). Once such a GAN is trained, the latent vector given as input to the GAN’s generator network can be put under evolutionary control, allowing controllable and high-quality image generation. In this paper, we demonstrate the advantage of this novel approach through a user study in which participants were able to evolve images that strongly resemble specific target images.
Tasks	Image Generation
Published	2018-01-24
URL	http://arxiv.org/abs/1801.08230v1
PDF	http://arxiv.org/pdf/1801.08230v1.pdf
PWC	https://paperswithcode.com/paper/deep-interactive-evolution
Repo
Framework

Learning to Match via Inverse Optimal Transport


Title	Learning to Match via Inverse Optimal Transport
Authors	Ruilin Li, Xiaojing Ye, Haomin Zhou, Hongyuan Zha
Abstract	We propose a unified data-driven framework based on inverse optimal transport that can learn adaptive, nonlinear interaction cost function from noisy and incomplete empirical matching matrix and predict new matching in various matching contexts. We emphasize that the discrete optimal transport plays the role of a variational principle which gives rise to an optimization-based framework for modeling the observed empirical matching data. Our formulation leads to a non-convex optimization problem which can be solved efficiently by an alternating optimization method. A key novel aspect of our formulation is the incorporation of marginal relaxation via regularized Wasserstein distance, significantly improving the robustness of the method in the face of noisy or missing empirical matching data. Our model falls into the category of prescriptive models, which not only predict potential future matching, but is also able to explain what leads to empirical matching and quantifies the impact of changes in matching factors. The proposed approach has wide applicability including predicting matching in online dating, labor market, college application and crowdsourcing. We back up our claims with numerical experiments on both synthetic data and real world data sets.
Tasks
Published	2018-02-10
URL	http://arxiv.org/abs/1802.03644v3
PDF	http://arxiv.org/pdf/1802.03644v3.pdf
PWC	https://paperswithcode.com/paper/learning-to-match-via-inverse-optimal
Repo
Framework

Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application


Title	Deep Transfer Network with Joint Distribution Adaptation: A New Intelligent Fault Diagnosis Framework for Industry Application
Authors	Te Han, Chao Liu, Wenguang Yang, Dongxiang Jiang
Abstract	In recent years, an increasing popularity of deep learning model for intelligent condition monitoring and diagnosis as well as prognostics used for mechanical systems and structures has been observed. In the previous studies, however, a major assumption accepted by default, is that the training and testing data are taking from same feature distribution. Unfortunately, this assumption is mostly invalid in real application, resulting in a certain lack of applicability for the traditional diagnosis approaches. Inspired by the idea of transfer learning that leverages the knowledge learnt from rich labeled data in source domain to facilitate diagnosing a new but similar target task, a new intelligent fault diagnosis framework, i.e., deep transfer network (DTN), which generalizes deep learning model to domain adaptation scenario, is proposed in this paper. By extending the marginal distribution adaptation (MDA) to joint distribution adaptation (JDA), the proposed framework can exploit the discrimination structures associated with the labeled data in source domain to adapt the conditional distribution of unlabeled target data, and thus guarantee a more accurate distribution matching. Extensive empirical evaluations on three fault datasets validate the applicability and practicability of DTN, while achieving many state-of-the-art transfer results in terms of diverse operating conditions, fault severities and fault types.
Tasks	Domain Adaptation, Transfer Learning
Published	2018-04-18
URL	http://arxiv.org/abs/1804.07265v1
PDF	http://arxiv.org/pdf/1804.07265v1.pdf
PWC	https://paperswithcode.com/paper/deep-transfer-network-with-joint-distribution
Repo
Framework

Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC


Title	Bayesian Pose Graph Optimization via Bingham Distributions and Tempered Geodesic MCMC
Authors	Tolga Birdal, Umut Şimşekli, M. Onur Eken, Slobodan Ilic
Abstract	We introduce Tempered Geodesic Markov Chain Monte Carlo (TG-MCMC) algorithm for initializing pose graph optimization problems, arising in various scenarios such as SFM (structure from motion) or SLAM (simultaneous localization and mapping). TG-MCMC is first of its kind as it unites asymptotically global non-convex optimization on the spherical manifold of quaternions with posterior sampling, in order to provide both reliable initial poses and uncertainty estimates that are informative about the quality of individual solutions. We devise rigorous theoretical convergence guarantees for our method and extensively evaluate it on synthetic and real benchmark datasets. Besides its elegance in formulation and theory, we show that our method is robust to missing data, noise and the estimated uncertainties capture intuitive properties of the data.
Tasks	Simultaneous Localization and Mapping
Published	2018-05-31
URL	http://arxiv.org/abs/1805.12279v2
PDF	http://arxiv.org/pdf/1805.12279v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-pose-graph-optimization-via-bingham
Repo
Framework

Unsupervised Hyperalignment for Multilingual Word Embeddings


Title	Unsupervised Hyperalignment for Multilingual Word Embeddings
Authors	Jean Alaux, Edouard Grave, Marco Cuturi, Armand Joulin
Abstract	We consider the problem of aligning continuous word representations, learned in multiple languages, to a common space. It was recently shown that, in the case of two languages, it is possible to learn such a mapping without supervision. This paper extends this line of work to the problem of aligning multiple languages to a common space. A solution is to independently map all languages to a pivot language. Unfortunately, this degrades the quality of indirect word translation. We thus propose a novel formulation that ensures composable mappings, leading to better alignments. We evaluate our method by jointly aligning word vectors in eleven languages, showing consistent improvement with indirect mappings while maintaining competitive performance on direct word translation.
Tasks	Multilingual Word Embeddings, Word Embeddings
Published	2018-11-02
URL	https://arxiv.org/abs/1811.01124v3
PDF	https://arxiv.org/pdf/1811.01124v3.pdf
PWC	https://paperswithcode.com/paper/unsupervised-hyperalignment-for-multilingual
Repo
Framework

Benchmarks for Image Classification and Other High-dimensional Pattern Recognition Problems


Title	Benchmarks for Image Classification and Other High-dimensional Pattern Recognition Problems
Authors	Tarun Yellamraju, Jonas Hepp, Mireille Boutin
Abstract	A good classification method should yield more accurate results than simple heuristics. But there are classification problems, especially high-dimensional ones like the ones based on image/video data, for which simple heuristics can work quite accurately; the structure of the data in such problems is easy to uncover without any sophisticated or computationally expensive method. On the other hand, some problems have a structure that can only be found with sophisticated pattern recognition methods. We are interested in quantifying the difficulty of a given high-dimensional pattern recognition problem. We consider the case where the patterns come from two pre-determined classes and where the objects are represented by points in a high-dimensional vector space. However, the framework we propose is extendable to an arbitrarily large number of classes. We propose classification benchmarks based on simple random projection heuristics. Our benchmarks are 2D curves parameterized by the classification error and computational cost of these simple heuristics. Each curve divides the plane into a “positive- gain” and a “negative-gain” region. The latter contains methods that are ill-suited for the given classification problem. The former is divided into two by the curve asymptote; methods that lie in the small region under the curve but right of the asymptote merely provide a computational gain but no structural advantage over the random heuristics. We prove that the curve asymptotes are optimal (i.e. at Bayes error) in some cases, and thus no sophisticated method can provide a structural advantage over the random heuristics. Such classification problems, an example of which we present in our numerical experiments, provide poor ground for testing new pattern classification methods.
Tasks	Image Classification
Published	2018-06-13
URL	http://arxiv.org/abs/1806.05272v1
PDF	http://arxiv.org/pdf/1806.05272v1.pdf
PWC	https://paperswithcode.com/paper/benchmarks-for-image-classification-and-other
Repo
Framework

DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal


Title	DMCNN: Dual-Domain Multi-Scale Convolutional Neural Network for Compression Artifacts Removal
Authors	Xiaoshuai Zhang, Wenhan Yang, Yueyu Hu, Jiaying Liu
Abstract	JPEG is one of the most commonly used standards among lossy image compression methods. However, JPEG compression inevitably introduces various kinds of artifacts, especially at high compression rates, which could greatly affect the Quality of Experience (QoE). Recently, convolutional neural network (CNN) based methods have shown excellent performance for removing the JPEG artifacts. Lots of efforts have been made to deepen the CNNs and extract deeper features, while relatively few works pay attention to the receptive field of the network. In this paper, we illustrate that the quality of output images can be significantly improved by enlarging the receptive fields in many cases. One step further, we propose a Dual-domain Multi-scale CNN (DMCNN) to take full advantage of redundancies on both the pixel and DCT domains. Experiments show that DMCNN sets a new state-of-the-art for the task of JPEG artifact removal.
Tasks	Image Compression, JPEG Artifact Removal
Published	2018-06-08
URL	http://arxiv.org/abs/1806.03275v2
PDF	http://arxiv.org/pdf/1806.03275v2.pdf
PWC	https://paperswithcode.com/paper/dmcnn-dual-domain-multi-scale-convolutional
Repo
Framework

DeepSDCS: Dissecting cancer proliferation heterogeneity in Ki67 digital whole slide images


Title	DeepSDCS: Dissecting cancer proliferation heterogeneity in Ki67 digital whole slide images
Authors	Priya Lakshmi Narayanan, Shan E Ahmed Raza, Andrew Dodson, Barry Gusterson, Mitchell Dowsett, Yinyin Yuan
Abstract	Ki67 is an important biomarker for breast cancer. Classification of positive and negative Ki67 cells in histology slides is a common approach to determine cancer proliferation status. However, there is a lack of generalizable and accurate methods to automate Ki67 scoring in large-scale patient cohorts. In this work, we have employed a novel deep learning technique based on hypercolumn descriptors for cell classification in Ki67 images. Specifically, we developed the Simultaneous Detection and Cell Segmentation (DeepSDCS) network to perform cell segmentation and detection. VGG16 network was used for the training and fine tuning to training data. We extracted the hypercolumn descriptors of each cell to form the vector of activation from specific layers to capture features at different granularity. Features from these layers that correspond to the same pixel were propagated using a stochastic gradient descent optimizer to yield the detection of the nuclei and the final cell segmentations. Subsequently, seeds generated from cell segmentation were propagated to a spatially constrained convolutional neural network for the classification of the cells into stromal, lymphocyte, Ki67-positive cancer cell, and Ki67-negative cancer cell. We validated its accuracy in the context of a large-scale clinical trial of oestrogen-receptor-positive breast cancer. We achieved 99.06% and 89.59% accuracy on two separate test sets of Ki67 stained breast cancer dataset comprising biopsy and whole-slide images.
Tasks	Cell Segmentation
Published	2018-06-28
URL	http://arxiv.org/abs/1806.10850v1
PDF	http://arxiv.org/pdf/1806.10850v1.pdf
PWC	https://paperswithcode.com/paper/deepsdcs-dissecting-cancer-proliferation
Repo
Framework

A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning


Title	A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning
Authors	Amy Zhang, Nicolas Ballas, Joelle Pineau
Abstract	The risks and perils of overfitting in machine learning are well known. However most of the treatment of this, including diagnostic tools and remedies, was developed for the supervised learning case. In this work, we aim to offer new perspectives on the characterization and prevention of overfitting in deep Reinforcement Learning (RL) methods, with a particular focus on continuous domains. We examine several aspects, such as how to define and diagnose overfitting in MDPs, and how to reduce risks by injecting sufficient training diversity. This work complements recent findings on the brittleness of deep RL methods and offers practical observations for RL researchers and practitioners.
Tasks
Published	2018-06-20
URL	http://arxiv.org/abs/1806.07937v2
PDF	http://arxiv.org/pdf/1806.07937v2.pdf
PWC	https://paperswithcode.com/paper/a-dissection-of-overfitting-and
Repo
Framework

Microscopy Cell Segmentation via Convolutional LSTM Networks


Title	Microscopy Cell Segmentation via Convolutional LSTM Networks
Authors	Assaf Arbelle, Tammy Riklin Raviv
Abstract	Live cell microscopy sequences exhibit complex spatial structures and complicated temporal behaviour, making their analysis a challenging task. Considering cell segmentation problem, which plays a significant role in the analysis, the spatial properties of the data can be captured using Convolutional Neural Networks (CNNs). Recent approaches show promising segmentation results using convolutional encoder-decoders such as the U-Net. Nevertheless, these methods are limited by their inability to incorporate temporal information, that can facilitate segmentation of individual touching cells or of cells that are partially visible. In order to exploit cell dynamics we propose a novel segmentation architecture which integrates Convolutional Long Short Term Memory (C-LSTM) with the U-Net. The network’s unique architecture allows it to capture multi-scale, compact, spatio-temporal encoding in the C-LSTMs memory units. The method was evaluated on the Cell Tracking Challenge and achieved state-of-the-art results (1st on Fluo-N2DH-SIM+ and 2nd on DIC-C2DL-HeLa datasets) The code is freely available at: https://github.com/arbellea/LSTM-UNet.git
Tasks	Cell Segmentation
Published	2018-05-29
URL	http://arxiv.org/abs/1805.11247v2
PDF	http://arxiv.org/pdf/1805.11247v2.pdf
PWC	https://paperswithcode.com/paper/microscopy-cell-segmentation-via
Repo
Framework